Aravind Srinivas· @AravSrinivas · X·· 3 小时前精选AI 评分65
AI 导读
Perplexity 开源 pplx-embed-v2-late，这是面向文本和图像的多向量嵌入模型，提供 9B 和 0.6B 两个版本，共享同一嵌入空间。9B 可用于索引多模态数据，0.6B 可在端侧做查询，并支持无需 OCR 直接检索 PDF 页面。官方称其在 MADQA 上得分 92.4%，在 BrowseComp+ 上得分 64%，权重已在 Hugging Face 发布。
推荐理由
Perplexity 开源多向量嵌入模型，9B 建索引、0.6B 端侧查询，并给出 MADQA 与 BrowseComp+ 分数。
正文 · 原文
We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device with 0.6B. This also enables you to search over PDF pages with no OCR. And scores 92.4% on MADQA, 64% on BrowseComp+. Weights available on @huggingface now.
We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying. Both models achieve frontier performance and are publicly available on Hugging Face. https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector在 X 查看被引用的帖子
来源：Aravind Srinivas · x.com